April 2, 2020

3188 words 15 mins read

Paper Group ANR 352

HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images. Injective Domain Knowledge in Neural Networks for Transprecision Computing. Adaptive Hyper-box Matching for Interpretable Individualized Treatment Effect Estimation. A machine learning environment for evaluating autonomous driving software. Decisions, Counterfa …

HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images


Title	HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images
Authors	Johan Vertens, Jannik Zürn, Wolfram Burgard
Abstract	The majority of learning-based semantic segmentation methods are optimized for daytime scenarios and favorable lighting conditions. Real-world driving scenarios, however, entail adverse environmental conditions such as nighttime illumination or glare which remain a challenge for existing approaches. In this work, we propose a multimodal semantic segmentation model that can be applied during daytime and nighttime. To this end, besides RGB images, we leverage thermal images, making our network significantly more robust. We avoid the expensive annotation of nighttime images by leveraging an existing daytime RGB-dataset and propose a teacher-student training approach that transfers the dataset’s knowledge to the nighttime domain. We further employ a domain adaptation method to align the learned feature spaces across the domains and propose a novel two-stage training scheme. Furthermore, due to a lack of thermal data for autonomous driving, we present a new dataset comprising over 20,000 time-synchronized and aligned RGB-thermal image pairs. In this context, we also present a novel target-less calibration method that allows for automatic robust extrinsic and intrinsic thermal camera calibration. Among others, we employ our new dataset to show state-of-the-art results for nighttime semantic segmentation.
Tasks	Autonomous Driving, Calibration, Domain Adaptation, Semantic Segmentation
Published	2020-03-10
URL	https://arxiv.org/abs/2003.04645v1
PDF	https://arxiv.org/pdf/2003.04645v1.pdf
PWC	https://paperswithcode.com/paper/heatnet-bridging-the-day-night-domain-gap-in
Repo
Framework

Injective Domain Knowledge in Neural Networks for Transprecision Computing


Title	Injective Domain Knowledge in Neural Networks for Transprecision Computing
Authors	Andrea Borghesi, Federico Baldo, Michele Lombardi, Michela Milano
Abstract	Machine Learning (ML) models are very effective in many learning tasks, due to the capability to extract meaningful information from large data sets. Nevertheless, there are learning problems that cannot be easily solved relying on pure data, e.g. scarce data or very complex functions to be approximated. Fortunately, in many contexts domain knowledge is explicitly available and can be used to train better ML models. This paper studies the improvements that can be obtained by integrating prior knowledge when dealing with a non-trivial learning task, namely precision tuning of transprecision computing applications. The domain information is injected in the ML models in different ways: I) additional features, II) ad-hoc graph-based network topology, III) regularization schemes. The results clearly show that ML models exploiting problem-specific information outperform the purely data-driven ones, with an average accuracy improvement around 38%.
Tasks
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10214v1
PDF	https://arxiv.org/pdf/2002.10214v1.pdf
PWC	https://paperswithcode.com/paper/injective-domain-knowledge-in-neural-networks
Repo
Framework

Adaptive Hyper-box Matching for Interpretable Individualized Treatment Effect Estimation


Title	Adaptive Hyper-box Matching for Interpretable Individualized Treatment Effect Estimation
Authors	Marco Morucci, Vittorio Orlandi, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky
Abstract	We propose a matching method for observational data that matches units with others in unit-specific, hyper-box-shaped regions of the covariate space. These regions are large enough that many matches are created for each unit and small enough that the treatment effect is roughly constant throughout. The regions are found as either the solution to a mixed integer program, or using a (fast) approximation algorithm. The result is an interpretable and tailored estimate of a causal effect for each unit.
Tasks
Published	2020-03-03
URL	https://arxiv.org/abs/2003.01805v1
PDF	https://arxiv.org/pdf/2003.01805v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-hyper-box-matching-for-interpretable
Repo
Framework

A machine learning environment for evaluating autonomous driving software


Title	A machine learning environment for evaluating autonomous driving software
Authors	Jussi Hanhirova, Anton Debner, Matias Hyyppä, Vesa Hirvisalo
Abstract	Autonomous vehicles need safe development and testing environments. Many traffic scenarios are such that they cannot be tested in the real world. We see hybrid photorealistic simulation as a viable tool for developing AI (artificial intelligence) software for autonomous driving. We present a machine learning environment for detecting autonomous vehicle corner case behavior. Our environment is based on connecting the CARLA simulation software to TensorFlow machine learning framework and custom AI client software. The AI client software receives data from a simulated world via virtual sensors and transforms the data into information using machine learning models. The AI clients control vehicles in the simulated world. Our environment monitors the state assumed by the vehicle AIs to the ground truth state derived from the simulation model. Our system can search for corner cases where the vehicle AI is unable to correctly understand the situation. In our paper, we present the overall hybrid simulator architecture and compare different configurations. We present performance measurements from real setups, and outline the main parameters affecting the hybrid simulator performance.
Tasks	Autonomous Driving, Autonomous Vehicles
Published	2020-03-07
URL	https://arxiv.org/abs/2003.03576v1
PDF	https://arxiv.org/pdf/2003.03576v1.pdf
PWC	https://paperswithcode.com/paper/a-machine-learning-environment-for-evaluating
Repo
Framework

Decisions, Counterfactual Explanations and Strategic Behavior


Title	Decisions, Counterfactual Explanations and Strategic Behavior
Authors	Stratis Tsirtsis, Manuel Gomez-Rodriguez
Abstract	Data-driven predictive models are increasingly used to inform decisions that hold important consequences for individuals and society. As a result, decision makers are often obliged, even legally required, to provide explanations about their decisions. In this context, it has been increasingly argued that these explanations should help individuals understand what would have to change for these decisions to be beneficial ones. However, there has been little discussion on the possibility that individuals may use the above counterfactual explanations to invest effort strategically in order to maximize their chances of receiving a beneficial decision. In this paper, our goal is to find policies and counterfactual explanations that are optimal in terms of utility in such a strategic setting. To this end, we first show that, given a pre-defined policy, the problem of finding the optimal set of counterfactual explanations is NP-hard. However, we further show that the corresponding objective is nondecreasing and satisfies submodularity. Therefore, a standard greedy algorithm offers an approximation factor of $(1-1/e)$ at solving the problem. Additionally, we also show that the problem of jointly finding both the optimal policy and set of counterfactual explanations reduces to maximizing a non-monotone submodular function. As a result, we can use a recent randomized algorithm to solve the problem, which offers an approximation factor of $1/e$. Finally, we illustrate our theoretical findings by performing experiments on synthetic and real lending data.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04333v1
PDF	https://arxiv.org/pdf/2002.04333v1.pdf
PWC	https://paperswithcode.com/paper/decisions-counterfactual-explanations-and
Repo
Framework

Addressing multiple metrics of group fairness in data-driven decision making


Title	Addressing multiple metrics of group fairness in data-driven decision making
Authors	Marius Miron, Songül Tolan, Emilia Gómez, Carlos Castillo
Abstract	The Fairness, Accountability, and Transparency in Machine Learning (FAT-ML) literature proposes a varied set of group fairness metrics to measure discrimination against socio-demographic groups that are characterized by a protected feature, such as gender or race.Such a system can be deemed as either fair or unfair depending on the choice of the metric. Several metrics have been proposed, some of them incompatible with each other.We do so empirically, by observing that several of these metrics cluster together in two or three main clusters for the same groups and machine learning methods. In addition, we propose a robust way to visualize multidimensional fairness in two dimensions through a Principal Component Analysis (PCA) of the group fairness metrics. Experimental results on multiple datasets show that the PCA decomposition explains the variance between the metrics with one to three components.
Tasks	Decision Making
Published	2020-03-10
URL	https://arxiv.org/abs/2003.04794v1
PDF	https://arxiv.org/pdf/2003.04794v1.pdf
PWC	https://paperswithcode.com/paper/addressing-multiple-metrics-of-group-fairness
Repo
Framework

Neural network with data augmentation in multi-objective prediction of multi-stage pump


Title	Neural network with data augmentation in multi-objective prediction of multi-stage pump
Authors	Hang Zhao
Abstract	A multi-objective prediction method of multi-stage pump method based on neural network with data augmentation is proposed. In order to study the highly nonlinear relationship between key design variables and centrifugal pump external characteristic values (head and power), the neural network model (NN) is built in comparison with the quadratic response surface model (RSF), the radial basis Gaussian response surface model (RBF), and the Kriging model (KRG). The numerical model validation experiment of another type of single stage centrifugal pump showed that numerical model based on CFD is quite accurate and fair. All of prediction models are trained by 60 samples under the different combination of three key variables in design range respectively. The accuracy of the head and power based on the four predictions models are analyzed comparing with the CFD simulation values. The results show that the neural network model has better performance in all external characteristic values comparing with other three surrogate models. Finally, a neural network model based on data augmentation (NNDA) is proposed for the reason that simulation cost is too high and data is scarce in mechanical simulation field especially in CFD problems. The model with data augmentation can triple the data by interpolation at each sample point of different attributes. It shows that the performance of neural network model with data augmentation is better than former neural network model. Therefore, the prediction ability of NN is enhanced without more simulation costs. With data augmentation it can be a better prediction model used in solving the optimization problems of multistage pump for next optimization and generalized to finite element analysis optimization problems in future.
Tasks	Data Augmentation
Published	2020-02-04
URL	https://arxiv.org/abs/2002.02402v1
PDF	https://arxiv.org/pdf/2002.02402v1.pdf
PWC	https://paperswithcode.com/paper/neural-network-with-data-augmentation-in
Repo
Framework

Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling


Title	Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
Authors	Tong Che, Ruixiang Zhang, Jascha Sohl-Dickstein, Hugo Larochelle, Liam Paull, Yuan Cao, Yoshua Bengio
Abstract	We show that the sum of the implicit generator log-density $\log p_g$ of a GAN with the logit score of the discriminator defines an energy function which yields the true data density when the generator is imperfect but the discriminator is optimal, thus making it possible to improve on the typical generator (with implicit density $p_g$). To make that practical, we show that sampling from this modified density can be achieved by sampling in latent space according to an energy-based model induced by the sum of the latent prior log-density and the discriminator output score. This can be achieved by running a Langevin MCMC in latent space and then applying the generator function, which we call Discriminator Driven Latent Sampling~(DDLS). We show that DDLS is highly efficient compared to previous methods which work in the high-dimensional pixel space and can be applied to improve on previously trained GANs of many types. We evaluate DDLS on both synthetic and real-world datasets qualitatively and quantitatively. On CIFAR-10, DDLS substantially improves the Inception Score of an off-the-shelf pre-trained SN-GAN~\citep{sngan} from $8.22$ to $9.09$ which is even comparable to the class-conditional BigGAN~\citep{biggan} model. This achieves a new state-of-the-art in unconditional image synthesis setting without introducing extra parameters or additional training.
Tasks	Image Generation
Published	2020-03-12
URL	https://arxiv.org/abs/2003.06060v2
PDF	https://arxiv.org/pdf/2003.06060v2.pdf
PWC	https://paperswithcode.com/paper/your-gan-is-secretly-an-energy-based-model
Repo
Framework


Title	Blind Image Restoration without Prior Knowledge
Authors	Noam Elron, Shahar S. Yuval, Dmitry Rudoy, Noam Levy
Abstract	Many image restoration techniques are highly dependent on the degradation used during training, and their performance declines significantly when applied to slightly different input. Blind and universal techniques attempt to mitigate this by producing a trained model that can adapt to varying conditions. However, blind techniques to date require prior knowledge of the degradation process, and assumptions regarding its parameter-space. In this paper we present the Self-Normalization Side-Chain (SCNC), a novel approach to blind universal restoration in which no prior knowledge of the degradation is needed. This module can be added to any existing CNN topology, and is trained along with the rest of the network in an end-to-end manner. The imaging parameters relevant to the task, as well as their dynamics, are deduced from the variety in the training data. We apply our solution to several image restoration tasks, and demonstrate that the SNSC encodes the degradation-parameters, improving restoration performance.
Tasks	Image Restoration
Published	2020-03-03
URL	https://arxiv.org/abs/2003.01764v2
PDF	https://arxiv.org/pdf/2003.01764v2.pdf
PWC	https://paperswithcode.com/paper/blind-image-restoration-without-prior
Repo
Framework

Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study


Title	Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study
Authors	Assaf Dauber, Meir Feder, Tomer Koren, Roi Livni
Abstract	The notion of implicit bias, or implicit regularization, has been suggested as a means to explain the surprising generalization ability of modern-days overparameterized learning algorithms. This notion refers to the tendency of the optimization algorithm towards a certain structured solution that often generalizes well. Recently, several papers have studied implicit regularization and were able to identify this phenomenon in various scenarios. We revisit this paradigm in arguably the simplest non-trivial setup, and study the implicit bias of Stochastic Gradient Descent (SGD) in the context of Stochastic Convex Optimization. As a first step, we provide a simple construction that rules out the existence of a \emph{distribution-independent} implicit regularizer that governs the generalization ability of SGD. We then demonstrate a learning problem that rules out a very general class of \emph{distribution-dependent} implicit regularizers from explaining generalization, which includes strongly convex regularizers as well as non-degenerate norm-based regularizations. Certain aspects of our constructions point out to significant difficulties in providing a comprehensive explanation of an algorithm’s generalization performance by solely arguing about its implicit regularization properties.
Tasks
Published	2020-03-13
URL	https://arxiv.org/abs/2003.06152v1
PDF	https://arxiv.org/pdf/2003.06152v1.pdf
PWC	https://paperswithcode.com/paper/can-implicit-bias-explain-generalization
Repo
Framework

Learning to Switch Between Machines and Humans


Title	Learning to Switch Between Machines and Humans
Authors	Vahid Balazadeh Meresht, Abir De, Adish Singla, Manuel Gomez-Rodriguez
Abstract	Reinforcement learning algorithms have been mostly developed and evaluated under the assumption that they will operate in a fully autonomous manner—they will take all actions. However, in safety critical applications, full autonomy faces a variety of technical, societal and legal challenges, which have precluded the use of reinforcement learning policies in real-world systems. In this work, our goal is to develop algorithms that, by learning to switch control between machines and humans, allow existing reinforcement learning policies to operate under different automation levels. More specifically, we first formally define the learning to switch problem using finite horizon Markov decision processes. Then, we show that, if the human policy is known, we can find the optimal switching policy directly by solving a set of recursive equations using backwards induction. However, in practice, the human policy is often unknown. To overcome this, we develop an algorithm that uses upper confidence bounds on the human policy to find a sequence of switching policies whose total regret with respect to the optimal switching policy is sublinear. Simulation experiments on two important tasks in autonomous driving—lane keeping and obstacle avoidance—demonstrate the effectiveness of the proposed algorithms and illustrate our theoretical findings.
Tasks	Autonomous Driving
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04258v1
PDF	https://arxiv.org/pdf/2002.04258v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-switch-between-machines-and
Repo
Framework

LIBRE: The Multiple 3D LiDAR Dataset


Title	LIBRE: The Multiple 3D LiDAR Dataset
Authors	Alexander Carballo, Jacob Lambert, Abraham Monrroy, David Wong, Patiphon Narksri, Yuki Kitsukawa, Eijiro Takeuchi, Shinpei Kato, Kazuya Takeda
Abstract	In this work, we present LIBRE: LiDAR Benchmarking and Reference, a first-of-its-kind dataset featuring 12 different LiDAR sensors, covering a range of manufacturers, models, and laser configurations. Data captured independently from each sensor includes four different environments and configurations: static obstacles placed at known distances and measured from a fixed position within a controlled environment; static obstacles measured from a moving vehicle, captured in a weather chamber where LiDARs were exposed to different conditions (fog, rain, strong light); dynamic objects actively measured from a fixed position by multiple LiDARs mounted side-by-side simultaneously, creating indirect interference conditions; and dynamic traffic objects captured from a vehicle driven on public urban roads multiple times at different times of the day, including data from supporting sensors such as cameras, infrared imaging, and odometry devices. LIBRE will contribute the research community to (1) provide a means for a fair comparison of currently available LiDARs, and (2) facilitate the improvement of existing self-driving vehicles and robotics-related software, in terms of development and tuning of LiDAR-based perception algorithms.
Tasks
Published	2020-03-13
URL	https://arxiv.org/abs/2003.06129v1
PDF	https://arxiv.org/pdf/2003.06129v1.pdf
PWC	https://paperswithcode.com/paper/libre-the-multiple-3d-lidar-dataset
Repo
Framework

Non-Intrusive Detection of Adversarial Deep Learning Attacks via Observer Networks


Title	Non-Intrusive Detection of Adversarial Deep Learning Attacks via Observer Networks
Authors	Kirthi Shankar Sivamani, Rajeev Sahay, Aly El Gamal
Abstract	Recent studies have shown that deep learning models are vulnerable to specifically crafted adversarial inputs that are quasi-imperceptible to humans. In this letter, we propose a novel method to detect adversarial inputs, by augmenting the main classification network with multiple binary detectors (observer networks) which take inputs from the hidden layers of the original network (convolutional kernel outputs) and classify the input as clean or adversarial. During inference, the detectors are treated as a part of an ensemble network and the input is deemed adversarial if at least half of the detectors classify it as so. The proposed method addresses the trade-off between accuracy of classification on clean and adversarial samples, as the original classification network is not modified during the detection process. The use of multiple observer networks makes attacking the detection mechanism non-trivial even when the attacker is aware of the victim classifier. We achieve a 99.5% detection accuracy on the MNIST dataset and 97.5% on the CIFAR-10 dataset using the Fast Gradient Sign Attack in a semi-white box setup. The number of false positive detections is a mere 0.12% in the worst case scenario.
Tasks
Published	2020-02-22
URL	https://arxiv.org/abs/2002.09772v1
PDF	https://arxiv.org/pdf/2002.09772v1.pdf
PWC	https://paperswithcode.com/paper/non-intrusive-detection-of-adversarial-deep
Repo
Framework

Adaptive Stopping Rule for Kernel-based Gradient Descent Algorithms


Title	Adaptive Stopping Rule for Kernel-based Gradient Descent Algorithms
Authors	Xiangyu Chang, Shao-Bo Lin
Abstract	In this paper, we propose an adaptive stopping rule for kernel-based gradient descent (KGD) algorithms. We introduce the empirical effective dimension to quantify the increments of iterations in KGD and derive an implementable early stopping strategy. We analyze the performance of the adaptive stopping rule in the framework of learning theory. Using the recently developed integral operator approach, we rigorously prove the optimality of the adaptive stopping rule in terms of showing the optimal learning rates for KGD equipped with this rule. Furthermore, a sharp bound on the number of iterations in KGD equipped with the proposed early stopping rule is also given to demonstrate its computational advantage.
Tasks
Published	2020-01-09
URL	https://arxiv.org/abs/2001.02879v1
PDF	https://arxiv.org/pdf/2001.02879v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-stopping-rule-for-kernel-based
Repo
Framework

Machine Learning Approaches For Motor Learning: A Short Review


Title	Machine Learning Approaches For Motor Learning: A Short Review
Authors	Baptiste Caramiaux, Jules Françoise, Abby Wanyu Liu, Téo Sanchez, Frédéric Bevilacqua
Abstract	The use of machine learning to model motor learning mechanisms is still limited, while it could help to design novel interactive systems for movement learning or rehabilitation. This approach requires to account for the motor variability induced by motor learning mechanisms. This represents specific challenges concerning fast adaptability of the computational models, from small variations to more drastic changes, including new movement classes. We propose a short review on machine learning based movement models and their existing adaptation mechanisms. We discuss the current challenges for applying these models in motor learning support systems, delineating promising research directions at the intersection of machine learning and motor learning.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04317v1
PDF	https://arxiv.org/pdf/2002.04317v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-approaches-for-motor
Repo
Framework